Update README.md
Browse files
README.md
CHANGED
@@ -15,7 +15,7 @@ pipeline_tag: text-generation
|
|
15 |
library_name: transformers
|
16 |
---
|
17 |
|
18 |
-
# Llama-Carvalho-
|
19 |
|
20 |
## Table of Contents
|
21 |
<details>
|
@@ -41,13 +41,13 @@ library_name: transformers
|
|
41 |
|
42 |
## Model description
|
43 |
|
44 |
-
**Llama-Carvalho-
|
45 |
It is the result of a continual pretraining of [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) with a multilingual corpus consisting of 540M tokens of plain text and 72M tokens of instructions (formated as plain text)
|
46 |
|
47 |
This model is part of the **Carvalho familily**, a family of LLMs specialized in Portuguese and Galician. Smaller models can be found [here](https://huggingface.co/Nos-PT/Carvalho_pt-gl-1.3B)
|
48 |
## Intended uses and limitations
|
49 |
|
50 |
-
The **Llama-Carvalho-
|
51 |
It can perform text-generation tasks and be fine-tuned for specific scenarios.
|
52 |
|
53 |
## How to use
|
@@ -57,7 +57,7 @@ from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM
|
|
57 |
|
58 |
input_text = "Hoxe fai un bo d铆a. O sol "
|
59 |
|
60 |
-
model_id = "Nos-PT/Llama-Carvalho-
|
61 |
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
62 |
model = AutoModelForCausalLM.from_pretrained(model_id)
|
63 |
generator = pipeline(
|
|
|
15 |
library_name: transformers
|
16 |
---
|
17 |
|
18 |
+
# Llama-Carvalho-PT-GL
|
19 |
|
20 |
## Table of Contents
|
21 |
<details>
|
|
|
41 |
|
42 |
## Model description
|
43 |
|
44 |
+
**Llama-Carvalho-PT-GL** is a 8B-parameter transformer-based causal language model for Galician, Portuguese, Spanish and English.
|
45 |
It is the result of a continual pretraining of [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) with a multilingual corpus consisting of 540M tokens of plain text and 72M tokens of instructions (formated as plain text)
|
46 |
|
47 |
This model is part of the **Carvalho familily**, a family of LLMs specialized in Portuguese and Galician. Smaller models can be found [here](https://huggingface.co/Nos-PT/Carvalho_pt-gl-1.3B)
|
48 |
## Intended uses and limitations
|
49 |
|
50 |
+
The **Llama-Carvalho-PT-GL** model is ready-to-use only for causal language modeling.
|
51 |
It can perform text-generation tasks and be fine-tuned for specific scenarios.
|
52 |
|
53 |
## How to use
|
|
|
57 |
|
58 |
input_text = "Hoxe fai un bo d铆a. O sol "
|
59 |
|
60 |
+
model_id = "Nos-PT/Llama-Carvalho-PT-GL"
|
61 |
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
62 |
model = AutoModelForCausalLM.from_pretrained(model_id)
|
63 |
generator = pipeline(
|